search

rust-ml / linfa

A Rust machine learning framework.
Apache License 2.0
3.73k stars 243 forks source link

Would there be any interest in a Covariance module? #293

Open zdk123 opened 1 year ago

zdk123 commented 1 year ago

Similar to the scikit-learn module. I'm primarily interested in implementing the Graphical Lasso, but empirical and shrinkage covariance estimators as well.

YuhanLiin commented 1 year ago

I think you can put that into a new algorithm crate. What do you think @quietlychris @bytesnake

bytesnake commented 1 year ago

Hey Zachari, a covariance estimation crate would be a great addition to Linfa! Sparse covariance estimation should be not too hard, you can probably reuse routines for elasticnet solvers. Question is how to represent a structured covariance, ndarray currently only supports dense, no banded or sparse representation. If you have questions please let us know

26.02.2023 13:28:01 Yuhan Lin @.***>:

I think you can put that into a new algorithm crate. What do you think @quietlychris[https://github.com/quietlychris] @bytesnake[https://github.com/bytesnake]

— Reply to this email directly, view it on GitHub[https://github.com/rust-ml/linfa/issues/293#issuecomment-1445459142], or unsubscribe[https://github.com/notifications/unsubscribe-auth/AAHRRKKYQZ4QIQ6ZMQNK543WZO4EXANCNFSM6AAAAAAVITKABI]. You are receiving this because you were mentioned.[Verfolgungsbild][https://github.com/notifications/beacon/AAHRRKLXW77TZN5XLPAOIOTWZO4EXA5CNFSM6AAAAAAVITKABKWGG33NNVSW45C7OR4XAZNMJFZXG5LFINXW23LFNZ2KUY3PNVWWK3TUL5UWJTSWE72MM.gif]